mediacutlet / pocket-tank
A 14M-parameter LLM keeps a virtual fish tank alive on an $8 ESP32-S3 — distilled from a 26B teacher into 7.56 MB, no network.
Why this job: works in the areas we cover, but does not say which job it does
What it does
The ESP32-S3 board, with screen and battery used in this project is actually around $35.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 6 days ago
- Stars
- 273
- +7 this week
- Licence
- Custom
- Read before business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.4.1
- Released 6 days ago
- Built with
- C
- 94% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 57% closed
- 3 still open
- Pull requests
- 1 merged
- 10 waiting
- Releases
- 19
- 19 in the last year
- Contributing guide (opens in new tab)
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| SensorsIot / Embedded-AI-Harness | 286 | 34 days ago | MIT | No downloads |
| horus-ai-labs / DistillFlow | 169 | 53 days ago | Apache-2.0 | No downloads |
| minorcell / spider | 13 | yesterday | MIT | No downloads |
More: languages, topics and project record
Languages
- C 94%
- C++ 3%
- Python 3%
- Shell <1%
Topics
- distillation
- embedded
- esp32
- llama2c
- llm
- lvgl
- virtual-pet
Project record
- JobOther AI tools
- StatusListed
- Commits86
- Forks70
- Watching7
- Stars in 28 days+56
- CreatedAug 24, 2026
- First seen by usNov 7, 2026
- CheckedNov 8, 2026